Module Title:   Intelligent Sensor Fusion

Module Credit:   10

Module Code:   ENG4083M

Academic Year:   2015/6

Teaching Period:   Semester 1

Module Occurrence:   A

Module Level:   FHEQ Level 7

Module Type:   Standard module

Provider:   Engineering

Related Department/Subject Area:   PI - Engineering: Telecomms, Electromagnetics etc (MDIS) (not in use)

Principal Co-ordinator:   Dr JC Readle

Additional Tutor(s):   -

Prerequisite(s):   None

Corequisite(s):   None

Aims:
To provide students with a thorough understanding of the techniques and tools used to develop intelligent multi-sensor data fusion applications.

Learning Teaching & Assessment Strategy:
Theoretical material is introduced through formal lectures and directed study, and assessed by a written examination. The application of the concepts is developed through one or more case studies in the seminars and the laboratory. An understanding of the application of the concepts is assessed by the laboratory-based coursework. The supplementary assessment for the coursework component will be to repair the deficiencies in the original.

Lectures:   12.00          Directed Study:   74.50           
Seminars/Tutorials:   4.00          Other:   0.00           
Laboratory/Practical:   8.00          Formal Exams:   1.50          Total:   100.00

On successful completion of this module you will be able to...

1.1 Critically evaluate and analyse the concepts of applied artificial intelligence.
1.2 Critically evaluate and analyse the design methodology and implementation techniques of multi-sensor data fusion.

On successful completion of this module you will be able to...

2.1 Critically analyse and apply fundamental concepts to the design and programming of advanced intelligent multi-sensor data fusion applications.

On successful completion of this module you will be able to...

3.1 Demonstrate problem solving, critical analysis, and written presentation skills.

  Examination - closed book 1.50 70%
 
  Examination closed book
  Coursework   30%
 
  1000 word report equivalent

Outline Syllabus:
Basic principles of multi-sensor data fusion: review of wide range of approaches including statistical intelligent techniques and Kalman filters. Overview of classical sensor fusion problems including weather forecasting and command and control systems. Consideration of AI based techniques in more detail. Artificial neural networks, including configurations, training and implementation. Fuzzy logic, theory and implementation. Hybrid neuro-fuzzy systems. One or more extended case studies.

Version No:  1